Examples of java.text.CharacterIterator

java.text.CharacterIterator
This interface defines a protocol for bidirectional iteration over text. The iterator iterates over a bounded sequence of characters. Characters are indexed with values beginning with the value returned by getBeginIndex() and continuing through the value returned by getEndIndex()-1.
Iterators maintain a current character index, whose valid range is from getBeginIndex() to getEndIndex(); the value getEndIndex() is included to allow handling of zero-length text ranges and for historical reasons. The current index can be retrieved by calling getIndex() and set directly by calling setIndex(), first(), and last().
The methods previous() and next() are used for iteration. They return DONE if they would move outside the range from getBeginIndex() to getEndIndex() -1, signaling that the iterator has reached the end of the sequence. DONE is also returned by other methods to indicate that the current index is outside this range.
Examples:
Traverse the text from start to finish
```
 public void traverseForward(CharacterIterator iter) { for(char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) { processChar(c); } } 
```
Traverse the text backwards, from end to start
```
 public void traverseBackward(CharacterIterator iter) { for(char c = iter.last(); c != CharacterIterator.DONE; c = iter.previous()) { processChar(c); } } 
```
Traverse both forward and backward from a given position in the text. Calls to notBoundary() in this example represents some additional stopping criteria.
```
 public void traverseOut(CharacterIterator iter, int pos) { for (char c = iter.setIndex(pos); c != CharacterIterator.DONE && notBoundary(c); c = iter.next()) { } int end = iter.getIndex(); for (char c = iter.setIndex(pos); c != CharacterIterator.DONE && notBoundary(c); c = iter.previous()) { } int start = iter.getIndex(); processSection(start, end); } 
```
@see StringCharacterIterator @see AttributedCharacterIterator

        }
    }
    if (canAccessClipboard) {
        String label = "";
        if (o instanceof CharacterIterator) {
      CharacterIterator iter = (CharacterIterator) o;
      char[] cbuff = new char[iter.getEndIndex()-iter.getBeginIndex()];
      if (cbuff.length > 0) {
          cbuff[0] = iter.first();
      }
      for (int i=1; i<cbuff.length;++i) {
          cbuff[i] = iter.next();
      }
      label = new String(cbuff);
        }
        Clipboard clipboard = Toolkit.getDefaultToolkit().getSystemClipboard();
        StringSelection selection = new StringSelection(label);

View Full Code Here

   *  <li>any other character is printed as-is</li>
   * </ul>
   */
  static String escapeText(String input) {
    StringBuilder builder = new StringBuilder(input.length());
    CharacterIterator iter = new StringCharacterIterator(input);
    for(char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
      switch(c) {
        case '\b':
          builder.append("\\b");
          break;
        case '\f':
          builder.append("\\f");
          break;
        case '\n':
          builder.append("\\n");
          break;
        case '\r':
          builder.append("\\r");
          break;
        case '\t':
          builder.append("\\t");
          break;
        case '\\':
          builder.append("\\\\");
          break;
        case '"':
          builder.append("\\\"");
          break;
        default:
          // Check for other control characters
          if(c >= 0x0000 && c <= 0x001F) {
            appendEscapedUnicode(builder, c);
          } else if(Character.isHighSurrogate(c)) {
            // Encode the surrogate pair using 2 six-character sequence (\\uXXXX\\uXXXX)
            appendEscapedUnicode(builder, c);
            c = iter.next();
            if(c == CharacterIterator.DONE) throw new IllegalArgumentException("invalid unicode string: unexpected high surrogate pair value without corresponding low value.");
            appendEscapedUnicode(builder, c);
          } else {
            // Anything else can be printed as-is
            builder.append(c);

View Full Code Here

     * @return -1 when not match; offset of the end of matched string when match.
     */
    private int matchCharacterIterator (Context con, Op op, int offset, int dx, int opts) {




        CharacterIterator target = con.ciTarget;












        while (true) {
            if (op == null)
                return offset;
            if (offset > con.limit || offset < con.start)
                return -1;
            switch (op.type) {
            case Op.CHAR:
                if (isSet(opts, IGNORE_CASE)) {
                    int ch = op.getData();
                    if (dx > 0) {
                        if (offset >= con.limit || !matchIgnoreCase(ch,  target .setIndex(  offset ) ))
                            return -1;
                        offset ++;
                    } else {
                        int o1 = offset-1;
                        if (o1 >= con.limit || o1 < 0 || !matchIgnoreCase(ch,  target .setIndex(  o1 ) ))
                            return -1;
                        offset = o1;
                    }
                } else {
                    int ch = op.getData();
                    if (dx > 0) {
                        if (offset >= con.limit || ch !=  target .setIndex(  offset ) )
                            return -1;
                        offset ++;
                    } else {
                        int o1 = offset-1;
                        if (o1 >= con.limit || o1 < 0 || ch !=  target .setIndex(  o1 ) )
                            return -1;
                        offset = o1;
                    }
                }
                op = op.next;
                break;


            case Op.DOT:
                if (dx > 0) {
                    if (offset >= con.limit)
                        return -1;
                    int ch =  target .setIndex(  offset ) ;
                    if (isSet(opts, SINGLE_LINE)) {
                        if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                            offset ++;
                    } else {
                        if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                            ch = REUtil.composeFromSurrogates(ch,  target .setIndex(  ++offset ) );
                        if (isEOLChar(ch))
                            return -1;
                    }
                    offset ++;
                } else {
                    int o1 = offset-1;
                    if (o1 >= con.limit || o1 < 0)
                        return -1;
                    int ch =  target .setIndex(  o1 ) ;
                    if (isSet(opts, SINGLE_LINE)) {
                        if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                            o1 --;
                    } else {
                        if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                            ch = REUtil.composeFromSurrogates( target .setIndex(  --o1 ) , ch);
                        if (!isEOLChar(ch))
                            return -1;
                    }
                    offset = o1;
                }
                op = op.next;
                break;


            case Op.RANGE:
            case Op.NRANGE:
                if (dx > 0) {
                    if (offset >= con.limit)
                        return -1;
                    int ch =  target .setIndex(  offset ) ;
                    if (REUtil.isHighSurrogate(ch) && offset+1 < con.limit)
                        ch = REUtil.composeFromSurrogates(ch,  target .setIndex(  ++offset ) );
                    RangeToken tok = op.getToken();
                    if (isSet(opts, IGNORE_CASE)) {
                        tok = tok.getCaseInsensitiveToken();
                        if (!tok.match(ch)) {
                            if (ch >= 0x10000)  return -1;
                            char uch;
                            if (!tok.match(uch = Character.toUpperCase((char)ch))
                                && !tok.match(Character.toLowerCase(uch)))
                                return -1;
                        }
                    } else {
                        if (!tok.match(ch))  return -1;
                    }
                    offset ++;
                } else {
                    int o1 = offset-1;
                    if (o1 >= con.limit || o1 < 0)
                        return -1;
                    int ch =  target .setIndex(  o1 ) ;
                    if (REUtil.isLowSurrogate(ch) && o1-1 >= 0)
                        ch = REUtil.composeFromSurrogates( target .setIndex(  --o1 ) , ch);
                    RangeToken tok = op.getToken();
                    if (isSet(opts, IGNORE_CASE)) {
                        tok = tok.getCaseInsensitiveToken();
                        if (!tok.match(ch)) {
                            if (ch >= 0x10000)  return -1;
                            char uch;
                            if (!tok.match(uch = Character.toUpperCase((char)ch))
                                && !tok.match(Character.toLowerCase(uch)))
                                return -1;
                        }
                    } else {
                        if (!tok.match(ch))  return -1;
                    }
                    offset = o1;
                }
                op = op.next;
                break;


            case Op.ANCHOR:
                boolean go = false;
                switch (op.getData()) {
                case '^':
                    if (isSet(opts, MULTIPLE_LINES)) {
                        if (!(offset == con.start
                              || offset > con.start && isEOLChar( target .setIndex(  offset-1 ) )))
                            return -1;
                    } else {
                        if (offset != con.start)
                            return -1;
                    }
                    break;


                case '@':                         // Internal use only.
                    // The @ always matches line beginnings.
                    if (!(offset == con.start
                          || offset > con.start && isEOLChar( target .setIndex(  offset-1 ) )))
                        return -1;
                    break;


                case '$':
                    if (isSet(opts, MULTIPLE_LINES)) {
                        if (!(offset == con.limit
                              || offset < con.limit && isEOLChar( target .setIndex(  offset ) )))
                            return -1;
                    } else {
                        if (!(offset == con.limit
                              || offset+1 == con.limit && isEOLChar( target .setIndex(  offset ) )
                              || offset+2 == con.limit &&  target .setIndex(  offset )  == CARRIAGE_RETURN
                              &&  target .setIndex(  offset+1 )  == LINE_FEED))
                            return -1;
                    }
                    break;


                case 'A':
                    if (offset != con.start)  return -1;
                    break;


                case 'Z':
                    if (!(offset == con.limit
                          || offset+1 == con.limit && isEOLChar( target .setIndex(  offset ) )
                          || offset+2 == con.limit &&  target .setIndex(  offset )  == CARRIAGE_RETURN
                          &&  target .setIndex(  offset+1 )  == LINE_FEED))
                        return -1;
                    break;


                case 'z':
                    if (offset != con.limit)  return -1;

View Full Code Here

        public void validate() {
            if (!isValid()) {
                TextNode textNode = (TextNode)getNode();


                int breakWidth = getBreakWidth();
                CharacterIterator ci = textNode.getCharacterIterator(start);


                float lineWidth = 0;
                int lastWhitespaceIndex = -1;


                char c = ci.first();
                while (c != CharacterIterator.DONE
                    && lineWidth < breakWidth) {
                    if (Character.isWhitespace(c)) {
                        lastWhitespaceIndex = ci.getIndex();
                    }


                    int i = ci.getIndex();
                    Rectangle2D characterBounds = font.getStringBounds(ci, i, i + 1,
                        FONT_RENDER_CONTEXT);
                    lineWidth += characterBounds.getWidth();


                    c = ci.current();
                }


                int end;
                if (lineWidth <= breakWidth) {
                    end = ci.getEndIndex();
                } else {
                    if (lastWhitespaceIndex == -1) {
                        end = ci.getIndex() - 1;
                        if (end <= start) {
                            end = start + 1;
                        }
                    } else {
                        end = lastWhitespaceIndex + 1;
                    }
                }


                glyphVector = font.createGlyphVector(FONT_RENDER_CONTEXT,
                    textNode.getCharacterIterator(start, end));


                if (end < ci.getEndIndex()) {
                    length = end - start;
                    next = new TextNodeView(textNode, end);
                } else {
                    length = ci.getEndIndex() - start;
                }


                Rectangle2D textBounds = glyphVector.getLogicalBounds();
                setSize((int)Math.ceil(textBounds.getWidth()),
                    (int)Math.ceil(textBounds.getHeight()));

View Full Code Here


        if (textNode != null) {
            int n = textNode.getCharacterCount();


            if (n > 0) {
                CharacterIterator ci = null;
                if (textInput.isPassword()) {
                    StringBuilder buf = new StringBuilder(n);
                    for (int i = 0; i < n; i++) {
                        buf.append(BULLET);
                    }

View Full Code Here

            // Not big enough to have an encoded sequence
            return encodedText;
        }
        StringBuilder sb = new StringBuilder();
        char[] digits = new char[4];
        CharacterIterator iter = new StringCharacterIterator(encodedText);
        for (char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
            if (c == '_') {
                // Read the next character, if there is one ...
                char next = iter.next();
                if (next == CharacterIterator.DONE) {
                    sb.append(c);
                    break;
                }
                // If the next character is not 'x', then these are just regular characters ...
                if (next != 'x') {
                    sb.append(c).append(next);
                    continue;
                }
                // Read the next 4 characters (digits) and another '_' character ...
                digits[0] = iter.next();
                if (digits[0] == CharacterIterator.DONE) {
                    sb.append(c).append(next);
                    break;
                }
                digits[1] = iter.next();
                if (digits[1] == CharacterIterator.DONE) {
                    sb.append(c).append(next).append(digits, 0, 1);
                    break;
                }
                digits[2] = iter.next();
                if (digits[2] == CharacterIterator.DONE) {
                    sb.append(c).append(next).append(digits, 0, 2);
                    break;
                }
                digits[3] = iter.next();
                if (digits[3] == CharacterIterator.DONE) {
                    sb.append(c).append(next).append(digits, 0, 3);
                    break;
                }
                char underscore = iter.next();
                if (underscore != '_') { // includes DONE
                    sb.append(c).append(next).append(digits, 0, 4);
                    if (underscore == CharacterIterator.DONE) break;
                    sb.append(underscore);
                    continue;

View Full Code Here

    public String encode( String text ) {
        if (text == null) return null;
        if (text.length() == 0) return text;
        StringBuilder sb = new StringBuilder();
        String hex = null;
        CharacterIterator iter = new StringCharacterIterator(text);
        for (char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
            if (c == '_') {
                // Read the next character (if there is one) ...
                char next = iter.next();
                if (next == CharacterIterator.DONE) {
                    sb.append(c);
                    break;
                }
                // If the next character is not 'x', then these are just regular characters ...

View Full Code Here

     * @see org.jboss.dna.common.text.TextEncoder#encode(java.lang.String)
     */
    public String encode( String text ) {
        if (text == null) return null;
        StringBuilder sb = new StringBuilder();
        CharacterIterator iter = new StringCharacterIterator(text);
        for (char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
            switch (c) {
                case '&':
                    sb.append("&amp;");
                    break;
                case '"':

View Full Code Here

     * @see org.jboss.dna.common.text.TextDecoder#decode(java.lang.String)
     */
    public String decode( String encodedText ) {
        if (encodedText == null) return null;
        StringBuilder sb = new StringBuilder();
        CharacterIterator iter = new StringCharacterIterator(encodedText);
        for (char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
            if (c == '&') {
                int index = iter.getIndex();
                
                do {
                    c = iter.next();
                }
                while (c != CharacterIterator.DONE && c != ';');


                // We found a closing semicolon
                if (c == ';') {
                    String s = encodedText.substring(index + 1, iter.getIndex());
                    
                    if (SPECIAL_ENTITIES.containsKey(s)) {
                        sb.append(SPECIAL_ENTITIES.get(s));
                        continue;
                        
                    }
                    
                    if (s.length() > 0 && s.charAt(0) == '#') {
                        try {
                            sb.append((char) Short.parseShort(s.substring(1, s.length())));
                            continue;
                        }
                        catch (NumberFormatException nfe) {
                            // This is possible in malformed encodings, but let it fall through
                        }
                    }
                }
                
                // Malformed encoding, restore state and pass poorly encoded data back
                c = '&';
                iter.setIndex(index);                            
            }


            sb.append(c);


        }

View Full Code Here

     * {@inheritDoc}
     */
    public String encode( String publicName ) {
        if (publicName == null) return null;
        StringBuilder sb = new StringBuilder();
        CharacterIterator iter = new StringCharacterIterator(publicName);
        for (char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
            char mapped = c;
            if (c == '*') {
                mapped = '\uF02A';
            } else if (c == '/') {
                mapped = '\uF02F';

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of java.text.CharacterIterator

avrora.util.StringUtil

cn.bran.japid.util.DirUtil

com.hp.hpl.jena.n3.N3JenaWriterCommon

com.ibm.icu.dev.test.iterator.TestUCharacterIterator

com.ibm.icu.tests.BreakIteratorTest

com.ibm.icu.text.DictionaryBasedBreakIterator

com.ibm.icu.text.RuleBasedBreakIterator

com.ibm.icu.text.RuleBasedCollator

com.ibm.icu.text.ThaiBreakIterator

com.rabbitmq.tools.json.JSONWriter

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.